A competitive co-evolutionary cultural differential evolution and its application to constrained optimization in butane alkylation process

A competitive co-evolutionary cultural differential evolution (CCCDE) is proposed for constrained optimization problems. A center individual, which is a potential solution, is introduced in the belief space. Competitive strategy is used to realize the co-evolution of multi-population. A relative fitness, i.e. competitive fitness, is presented to establish a diversity mechanism, which helps to escape from local optima when individuals are premature. CCCDE algorithm is validated through comparisons with two representative constraint- handling methods using eleven benchmark constrained problems. We also studied how to choose three thresholds, which are employed in the diversity mechanism. Finally, CCCDE is applied to a real-world problem with the objective to maximize the profit of butane alkylation process. It shows better applicability and effectiveness when compared with three other algorithms.

[1]  A. Neumaier,et al.  A global optimization method, αBB, for general twice-differentiable constrained NLPs — I. Theoretical advances , 1998 .

[2]  Peter J. Angeline,et al.  Competitive Environments Evolve Better Solutions for Complex Tasks , 1993, ICGA.

[3]  Robert G. Reynolds,et al.  A Cultural Algorithm Framework to Evolve Multi-Agent Cooperation with Evolutionary Programming , 1997, Evolutionary Programming.

[4]  Robert G. Reynolds,et al.  Cultural swarms: knowledge-driven problem solving in social systems , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[5]  Huang Hai.  Research on Cultural Algorithm for Solving Nonlinear Constrained Optimization , 2007 .

[6]  G. McCormick,et al.  Selected applications of nonlinear programming , 1968 .

[7]  Carlos A. Coello Coello,et al.  A Cultural Algorithm for Constrained Optimization , 2002, MICAI.

[8]  Zbigniew Michalewicz,et al.  Evolutionary Algorithms, Homomorphous Mappings, and Constrained Parameter Optimization , 1999, Evolutionary Computation.

[9]  Jinwei Gu,et al.  A novel competitive co-evolutionary quantum genetic algorithm for stochastic job shop scheduling problem , 2010, Comput. Oper. Res..

[10]  Xingsheng Gu,et al.  Application of Cultural Algorithms to Earliness/Tardiness Flow Shop With Uncertain Processing Time , 2007, Third International Conference on Natural Computation (ICNC 2007).

[11]  Carlos A. Coello Coello,et al.  A Cultural Algorithm with Differential Evolution to Solve Constrained Optimization Problems , 2004, IBERAMIA.

[12]  Yu Liu,et al.  Center particle swarm optimization , 2007, Neurocomputing.

[13]  Xin Yao,et al.  Stochastic ranking for constrained evolutionary optimization , 2000, IEEE Trans. Evol. Comput..

[14]  Chen De-zhao.  Constrained ant colony system and its application in process optimization of butene alkylation , 2005 .

[15]  Carlos A. Coello Coello,et al.  Evolutionary multiobjective optimization using a cultural algorithm , 2003, Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706).

[16]  Robert G. Reynolds,et al.  Knowledge-based function optimization using fuzzy cultural algorithms with evolutionary programming , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[17]  R. Storn,et al.  Differential evolution a simple and efficient adaptive scheme for global optimization over continu , 1997 .